A New Method to Forecast of Office Building Electricity Consumption: Genetic Algorithm - Neural Network

Journal Title: Scholars Journal of Engineering and Technology - Year 2017, Vol 5, Issue 8

Abstract

Saving energy is becoming a trend in today's society, office as our research object, the power consumption is very huge. We can effectively predict and track the office electricity situation is more and more important. In this paper, we play the data advantage, use the neural network to do training, get the corresponding forecast value. In order to overcome the shortcomings of the slow convergence of the neural network and easy to fall into the local error, we combine the genetic algorithm to filter the weights and thresholds of the input layer and the hidden layer to speed up the training accuracy and efficiency. Through the actual data validation, we get the training error within 5.5%, the robustness is strong, and the genetic algorithm after the combination of time increased by 31%. Effectively proving the reliability of our model. Keywords: energy saving, power consumption, neural network.

Authors and Affiliations

Yuanyuan Hao

Keywords

Related Articles

Effects of Heat and Mass Flux to MHD Flow in Vertical Surface with Radiation Absorption

MHD flow of an electrically conducting, incompressible, viscous fluid past an impulsively moving isothermal vertical plate through porous medium in the presence of uniform suction, radiation absorption and chemical react...

Case Study on Preventive Maintenance Strategy of Off-Highway Truck

Present study developed the preventive maintenance strategy of the articulated off-highway truck to minimize the total maintenance cost, and maximize the utilization rate. After analyzed the field data, the original main...

Design of Automatic Liquid Mixing Device Based on PLC

Abstract: According to the technological requirements of the control system, the Siemens S7200PLC can operate the valve by liquid level sensor data, and complete automatically the liquid mixing in this liquid hybrid cont...

Preliminary studies of common effluent treatment waste sludge in manufacturing of solid block

A common effluent treatment waste sludge being largest industry in India faces problem of sludge disposal. In this study an attempt is made to reuse common effluent treatment waste water sludge in solid blocks. Common ef...

Rectangular group congruences on an epigroup

An epigroup is a semigroup in which some power of any element lies in a sub-group of the given semigroup. The rectangular group congruences on an epigroup are investigated. A characterization of rectangular group congrue...

Download PDF file
  • EP ID EP386703
  • DOI -
  • Views 82
  • Downloads 0

How To Cite

Yuanyuan Hao (2017). A New Method to Forecast of Office Building Electricity Consumption: Genetic Algorithm - Neural Network. Scholars Journal of Engineering and Technology, 5(8), 407-412. https://europub.co.uk/articles/-A-386703